AI Paper Atlas

Research map / Point clouds / Segmentation and detection

GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-based Transformer

Xin Jin, Haisheng Su, Cong Ma, Kai Liu, Wei Wu, Fei Hui, Junchi Yan

ICCV 2025 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace MLP voxel encoder with GeoFormer (graph-guided transformer) (ablation)voxel detector (CenterPoint-Pillar) · Waymo val Vehicle L2 (20% train)3D AP: 61.02 -> 62.95Improved
add geometry-guided edge re-weighting to a vanilla transformer encoder (ablation)GeoFormer · Waymo 20% train3D AP (Vehicle/Ped/Cyc): 62.33 -> 62.95; 66.02 -> 67.67; 64.19 -> 65.04Improved
replace Mamba encoder by GeoFormer (ablation)GeoFormer · Waymo 20% train3D AP Vehicle: 61.90 -> 62.95Improved
add GPE to PillarNetPillarNet · nuScenes valmAP: 55.3 -> 58.9Improved
add GPE to DSVTDSVT · nuScenes valmAP: 66.2 -> 66.5Improved
add GPE to HEDNetHEDNet · nuScenes valmAP: 66.5 -> 67.0Improved
add GPE to SAFDNetSAFDNet · nuScenes valmAP: 66.2 -> 66.7Improved
add GPE to VoxelMambaVoxelMamba · nuScenes valmAP: 67.2 -> 68.2Improved
use fully connected graph instead of distance-thresholded graph (0.5/2.0) (ablation)GeoFormer · nuScenes valmAP / NDS: 66.7 -> 66.4; 71.4 -> 70.8Hurt
reduce theta_max from 2.0 to 1.5 (ablation)GeoFormer · nuScenes valmAP / NDS: 66.7 -> 66.3; 71.4 -> 70.5Hurt
lower theta_min from 0.8 to 0.5 with theta_max fixed at 2.0 (ablation)GeoFormer · nuScenes valmAP / NDS: 66.5 -> 66.7; 71.0 -> 71.4Improved
replace Dyn/TANet voxel encoder with GPECenterPoint-Pillar · nuScenes valmAP / NDS: 49.9 -> 51.8; 58.5 -> 60.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy